Depression at Work

Exploring Depression in Major US Companies from Online Reviews

AutoODI
Fig. 1: Schematic of AutoODI. It consists of three blocks, which: 1) embed both the review and the ODI dimension's sentence definition; 2) compute the cosine similarity between the two embeddings; and 3) shortlist reviews by discarding those that are below a given similarity level.

Studies on depression in the workplace have mostly investigated its impact on individual employees. At the individual level, workplace depression leads to a significant loss of productivity and competitiveness for many organizations. However, little is known about its association with the company as a whole, or the state where the company is based. The problem is twofold: (a) the lack of scalable methodologies operationalizing depression in the specific context of the workplace, and (b) the lack of data documenting potential distress.

Now imagine if we could collect thousands of employees' reviews documenting their workplace experience and study workplace depression at the scale of whole companies, or even states where companies are based? In a joint study with researchers from GESIS (Germany), University College London, Kings College London, and University of Neuchâtel, Nokia Bell Labs researchers did exactly this is in their recently published study in the ACM Conference On Computer-Supported Cooperative Work And Social Computing (CSCW).

By adapting a work-related depression scale called Occupational Depression Inventory (ODI) and gathering more than 350K employee reviews of 104 major companies across the whole US for the (2008-2020) years, the researchers developed a deep-learning framework (called AutoODI) scoring these reviews on a composite ODI score (Fig. 1). The presence of ODI mentions manifested itself not only at micro-level (companies scoring high in ODI suffered from low stock growth) but also at macro-level (states hosting these companies were associated with high depression rates, talent shortage, and economic deprivation). This new way of applying AutoODI onto company reviews offers both theoretical implications for the literature in computational social science, occupational health and economic geography, and practical implications for companies and policy makers.

Publications

  • Depression at Work: Exploring Depression in Major US Companies from Online Reviews. ACM CSCW 2022. PDF